Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2203.11537 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909135178563584 |
|---|---|
| author | Basher, Abol Boutellier, Jani |
| author_facet | Basher, Abol Boutellier, Jani |
| contents | Dense point cloud generation from a sparse or incomplete point cloud is a crucial and challenging problem in 3D computer vision and computer graphics. So far, the existing methods are either computationally too expensive, suffer from limited resolution, or both. In addition, some methods are strictly limited to watertight surfaces -- another major obstacle for a number of applications. To address these issues, we propose a lightweight Convolutional Neural Network that learns and predicts the unsigned distance field for arbitrary 3D shapes for dense point cloud generation using the recently emerged concept of implicit function learning. Experiments demonstrate that the proposed architecture outperforms the state of the art by 7.8x less model parameters, 2.4x faster inference time and up to 24.8% improved generation quality compared to the state-of-the-art. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2203_11537 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Convolutional Neural Network-based Efficient Dense Point Cloud Generation using Unsigned Distance Fields Basher, Abol Boutellier, Jani Computer Vision and Pattern Recognition Dense point cloud generation from a sparse or incomplete point cloud is a crucial and challenging problem in 3D computer vision and computer graphics. So far, the existing methods are either computationally too expensive, suffer from limited resolution, or both. In addition, some methods are strictly limited to watertight surfaces -- another major obstacle for a number of applications. To address these issues, we propose a lightweight Convolutional Neural Network that learns and predicts the unsigned distance field for arbitrary 3D shapes for dense point cloud generation using the recently emerged concept of implicit function learning. Experiments demonstrate that the proposed architecture outperforms the state of the art by 7.8x less model parameters, 2.4x faster inference time and up to 24.8% improved generation quality compared to the state-of-the-art. |
| title | Convolutional Neural Network-based Efficient Dense Point Cloud Generation using Unsigned Distance Fields |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2203.11537 |